palmer-002-GGUF/README.md

base_model, datasets, inference, language, license, model_creator, model_name, pipeline_tag, quantized_by, tags

base_model	datasets	inference	language	license	model_creator	model_name	pipeline_tag	quantized_by	tags
appvoid/palmer-002	appvoid/no-prompt-15k	false	en	apache-2.0	appvoid	palmer-002	text-generation	afrideva	gguf ggml quantized q2_k q3_k_m q4_k_m q5_k_m q6_k q8_0

appvoid/palmer-002-GGUF

Quantized GGUF model files for palmer-002 from appvoid

Name	Quant method	Size
palmer-002.fp16.gguf	fp16	2.20 GB
palmer-002.q2_k.gguf	q2_k	483.12 MB
palmer-002.q3_k_m.gguf	q3_k_m	550.82 MB
palmer-002.q4_k_m.gguf	q4_k_m	668.79 MB
palmer-002.q5_k_m.gguf	q5_k_m	783.02 MB
palmer-002.q6_k.gguf	q6_k	904.39 MB
palmer-002.q8_0.gguf	q8_0	1.17 GB

Original Model Card:

palmer

a better base model

palmer is a series of ~1b parameters language models fine-tuned to be used as base models instead of using custom prompts for tasks. This means that it can be further fine-tuned on more data with custom prompts as usual or be used for downstream tasks as any base model you can get. The model has the best of both worlds: some "bias" to act as an assistant, but also the abillity to predict the next-word from its internet knowledge base. It's a 1.1b llama 2 model so you can use it with your favorite tools/frameworks.

evaluation

Model	ARC_C	HellaSwag	PIQA	Winogrande
tinyllama-2t	0.2807	0.5463	0.7067	0.5683
palmer-001	0.2807	0.5524	0.7106	0.5896
tinyllama-2.5t	0.3191	0.5896	0.7307	0.5872
palmer-002	0.3242	0.5956	0.7345	0.5888

training

Training took ~3.5 P100 gpu hours. It was trained on 15,000 gpt-4 shuffled samples. palmer was fine-tuned using lower learning rates ensuring it keeps as much general knowledge as possible.

prompt

no prompt